Runs - Knowledge Base Acceleration 2013¶

BIT-ECQ¶

Participants | Proceedings | Input | Appendix

Run ID: BIT-ECQ
Participant: BIT
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/27/2013
Type: automatic
Task: kba-ccr-2013
MD5: 675d456d0f41ef6700c60614e19afb5d
Run description: Entity and Redirect Pages'names(Wikipedia) or Display name in profile page (Twitter), query expansion with entites extraced from the wikipedia page content and existing citation artices, retrieve the documents from index and scaled the ranking score to (0,1000], ECQ means EntityCentricQuery

BIT-ECQUpdate¶

Participants | Proceedings | Input | Appendix

Run ID: BIT-ECQUpdate
Participant: BIT
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/4/2013
Type: automatic
Task: kba-ccr-2013
MD5: e1ae743784d01eac19cd6c7f74d24566
Run description: Update of basic ECQ query mehod, enrich citations for twitter entities. Entity and Redirect Pages'names(Wikipedia) or Display name in profile page (Twitter), query expansion with entites extraced from the wikipedia page content and existing citation artices, retrieve the documents from index and scaled the ranking score to (0,1000], ECQ means EntityCentricQuery

BIT-RFBurst¶

Participants | Proceedings | Input | Appendix

Run ID: BIT-RFBurst
Participant: BIT
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 636305bd76f5da49b6ae0dc028d92c74
Run description: Add wikipedia view count busrt as a feature in Random Forest ranking method, more prone to Vital classification, train a uniform model for both wiki and twitter entity.

BIT-RFBurst_1¶

Participants | Proceedings | Input | Appendix

Run ID: BIT-RFBurst_1
Participant: BIT
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 77e3a5b769c3cfec3176e1a9c8901d79
Run description: same as RFBust, while using kba2012 data as training data, Random Forest ranking method, train a gerneral model for all entities.

BIT-RFClassLoose¶

Participants | Proceedings | Input | Appendix

Run ID: BIT-RFClassLoose
Participant: BIT
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/4/2013
Type: automatic
Task: kba-ccr-2013
MD5: 2e8fafe9f897c4053f00c48f477a5185
Run description: Random Forest classification method, train a uniform model for both wiki and twitter entity.

BIT-RFClassStrict¶

Participants | Proceedings | Input | Appendix

Run ID: BIT-RFClassStrict
Participant: BIT
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/4/2013
Type: automatic
Task: kba-ccr-2013
MD5: 3f958c9a501955318f422c716f362392
Run description: Random Forest classification method, more prone to Vital classification, train a uniform model for both wiki and twitter entity.

BIT-RFDiffModel¶

Participants | Proceedings | Input | Appendix

Run ID: BIT-RFDiffModel
Participant: BIT
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: fee66b19083463809069d97b3f720dba
Run description: Train two different models for Twitter and Wikipeida entities respectively. Using Random Forest ranking method, default setting in ranklib

BIT-RFMultiModel¶

Participants | Proceedings | Input | Appendix

Run ID: BIT-RFMultiModel
Participant: BIT
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 24267dcd693576f8a8c64c680c38ac6e
Run description: Random Forest ranking method, more prone to Vital classification, train a independant model for each entity.

BIT-RFMultiModel_1¶

Participants | Proceedings | Input | Appendix

Run ID: BIT-RFMultiModel_1
Participant: BIT
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: a754ed31f8badbe32534a2a89e053764
Run description: same as RFMultiModel, Tuned parameters, Random Forest ranking method, more prone to Vital classification, train a independant model for each entity.

BIT-RFRankUniModel¶

Participants | Proceedings | Input | Appendix

Run ID: BIT-RFRankUniModel
Participant: BIT
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/4/2013
Type: automatic
Task: kba-ccr-2013
MD5: 001ff40de66799dce3979e263405ec81
Run description: Random Forest Ranking method, train a uniform model for both wiki and twitter entity.

CompInsights-ccr_baseline_1¶

Participants | Input | Appendix

Run ID: CompInsights-ccr_baseline_1
Participant: CompInsights
Track: Knowledge Base Acceleration
Year: 2013
Submission: 6/11/2013
Type: automatic
Task: kba-ssf-2013
MD5: da7cfaef0b2a1bc02031c4760928e6a2
Run description: Entity title strings, redirects, and hand-constructed names provided high-recall filter of 22M StreamItems, then any document containing one of the surface form names is ranked vital with confidence proportional to length of surface form name.

CompInsights-ssf_baseline_1¶

Participants | Input | Appendix

Run ID: CompInsights-ssf_baseline_1
Participant: CompInsights
Track: Knowledge Base Acceleration
Year: 2013
Submission: 6/11/2013
Type: automatic
Task: kba-ssf-2013
MD5: fec53338adabdc81a2bf861e37e99b72
Run description: Entity title strings, redirects, and hand-constructed names provided high-recall filter of 22M StreamItems, then any document containing one of the surface form names is ranked vital with confidence proportional to length of surface form name, and the longest sentence containing the longest surface form name is treated as a slot fill for all slot types for the given entity type.

CWI-J48_1213_13¶

Participants | Proceedings | Input | Appendix

Run ID: CWI-J48_1213_13
Participant: CWI
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/28/2013
Type: automatic
Task: kba-ssf-2013
MD5: 6023dc1f7cb181bb21c64ea403f67ef3
Run description: We have used a two-step approach. Step one uses Wikipedia name variants to filter documents and extract features. In step two, we use J48 as a classification algorithm. We have used kba2012 plus kba 2013 annotation for training Features used were googcle-cross-lingual dictionary, Jaccrd similarity, Cosine similarity, KL-divergence, PageRnk scores, Right and Left context, first and last mention positions .

CWI-J48_12_13¶

Participants | Proceedings | Input | Appendix

Run ID: CWI-J48_12_13
Participant: CWI
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/28/2013
Type: automatic
Task: kba-ssf-2013
MD5: 8c537f5fd33be012cf66347af812246c
Run description: We have used a two-step approach. Step one uses Wikipedia name variants to filter documents and extract features. In step two, we use J48 as a classification algorithm. We have used kba2012 annotation for training Features used were googcle-cross-lingual dictionary, Jaccrd similarity, Cosine similarity, KL-divergence, PageRnk scores, Right and Left context, first and last mention positions .

CWI-J48_13_13¶

Participants | Proceedings | Input | Appendix

Run ID: CWI-J48_13_13
Participant: CWI
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/28/2013
Type: automatic
Task: kba-ssf-2013
MD5: 382032e20f2d18e88bd1b6cd977066e9
Run description: We have used a two-step approach. Step one uses Wikipedia name variants to filter documents and extract features. In step two, we use J48 as a classification algorithm. We have used kba2013 annotation for training Features used were googcle-cross-lingual dictionary, Jaccrd similarity, Cosine similarity, KL-divergence, PageRnk scores, Right and Left context, first and last mention positions .

CWI-RM_all_1213_13¶

Participants | Proceedings | Input | Appendix

Run ID: CWI-RM_all_1213_13
Participant: CWI
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/28/2013
Type: automatic
Task: kba-ccr-2013
MD5: 25e58c0fe450f70ef7391d5082632a10
Run description: We have used a two-step approach. Step one uses Wikipedia name variants to filter documents and extract features. In step two, we use Random Forest as a classification algorithm. We have used kba2012 plus kba 2013 annotation for training Features used were googcle-cross-lingual dictionary, Jaccard similarity, Cosine similarity, KL-divergence, PageRnk scores, Right and Left context, first and last mention positions, body length, first pos form, mentioning body and some more features.

CWI-RM_all_12_13¶

Participants | Proceedings | Input | Appendix

Run ID: CWI-RM_all_12_13
Participant: CWI
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/28/2013
Type: automatic
Task: kba-ccr-2013
MD5: 53b8e6e4fa97f608342f0d7d1643aded
Run description: We have used a two-step approach. Step one uses Wikipedia name variants to filter documents and extract features. In step two, we use Random Forest as a classification algorithm. We have used annotation for training Features used were googcle-cross-lingual dictionary, Jaccard similarity, Cosine similarity, KL-divergence, PageRnk scores, Right and Left context, first and last mention positions, body length, first pos form, mentioning body and some more features.

CWI-RM_all_13_13¶

Participants | Proceedings | Input | Appendix

Run ID: CWI-RM_all_13_13
Participant: CWI
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/28/2013
Type: automatic
Task: kba-ccr-2013
MD5: 67d0fb786aaf3a450da2249ec1eb62c4
Run description: We have used a two-step approach. Step one uses Wikipedia name variants to filter documents and extract features. In step two, we use Random Forest as a classification algorithm. We have used kba2013 annotation for training. Features used were googcle-cross-lingual dictionary, Jaccard similarity, Cosine similarity, KL-divergence, PageRnk scores, Right and Left context, first and last mention positions, body length, first pos form, mentioning body and some more features.

CWI-RM_FPN_1213_13¶

Participants | Proceedings | Input | Appendix

Run ID: CWI-RM_FPN_1213_13
Participant: CWI
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/28/2013
Type: automatic
Task: kba-ssf-2013
MD5: ce86118b0ba593b7bb8bcd31d23a5b82
Run description: We have used a two-step approach. Step one uses Wikipedia name variants to filter documents and extract features. In step two, we use Random Forest as a classification algorithm. We have used kba2012 plus kba 2013 annotation for training Features used were googcle-cross-lingual dictionary, Jaccrd similarity, Cosine similarity, KL-divergence, PageRnk scores, Right and Left context, first and last mention positions, body length, first pos form, .

CWI-RM_FPN_12_13¶

Participants | Proceedings | Input | Appendix

Run ID: CWI-RM_FPN_12_13
Participant: CWI
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/28/2013
Type: automatic
Task: kba-ssf-2013
MD5: 7875e1ab4ff92ce7d1291f1c2e39c7b9
Run description: We have used a two-step approach. Step one uses Wikipedia name variants to filter documents and extract features. In step two, we use Random Forest as a classification algorithm. We have used kba2012 annotation for training Features used were googcle-cross-lingual dictionary, Jaccrd similarity, Cosine similarity, KL-divergence, PageRnk scores, Right and Left context, first and last mention positions, body length, first pos form, .

CWI-RM_FPN_13_13¶

Participants | Proceedings | Input | Appendix

Run ID: CWI-RM_FPN_13_13
Participant: CWI
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/28/2013
Type: automatic
Task: kba-ssf-2013
MD5: a38abfd49883225dcb724ac086251aa8
Run description: We have used a two-step approach. Step one uses Wikipedia name variants to filter documents and extract features. In step two, we use Random Forest as a classification algorithm. We have used kba2013 annotation for training. Features used were googcle-cross-lingual dictionary, Jaccrd similarity, Cosine similarity, KL-divergence, PageRnk scores, Right and Left context, first and last mention positions, body length, first pos form, .

CWI-RM_MB_1213_13¶

Participants | Proceedings | Input | Appendix

Run ID: CWI-RM_MB_1213_13
Participant: CWI
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/28/2013
Type: automatic
Task: kba-ccr-2013
MD5: e32eae0f5f5c06858b4c2f1036961175
Run description: We have used a two-step approach. Step one uses Wikipedia name variants to filter documents and extract features. In step two, we use Random Forest as a classification algorithm. We have used kba2012 plus kba 2013 annotation for training Features used were googcle-cross-lingual dictionary, Jaccrd similarity, Cosine similarity, KL-divergence, PageRnk scores, Right and Left context, first and last mention positions, body length, first pos form, mentioning body.

CWI-RM_MB_12_13¶

Participants | Proceedings | Input | Appendix

Run ID: CWI-RM_MB_12_13
Participant: CWI
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/28/2013
Type: automatic
Task: kba-ccr-2013
MD5: 54a9d36c4843624955fc1961edc5e54b
Run description: We have used a two-step approach. Step one uses Wikipedia name variants to filter documents and extract features. In step two, we use Random Forest as a classification algorithm. We have used kba2012 annotation for training Features used were googcle-cross-lingual dictionary, Jaccrd similarity, Cosine similarity, KL-divergence, PageRnk scores, Right and Left context, first and last mention positions, body length, first pos form, mentioning body.

CWI-RM_MB_13_13¶

Participants | Proceedings | Input | Appendix

Run ID: CWI-RM_MB_13_13
Participant: CWI
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/28/2013
Type: automatic
Task: kba-ccr-2013
MD5: cdeade4dead462d3b443cef59e69eb2e
Run description: We have used a two-step approach. Step one uses Wikipedia name variants to filter documents and extract features. In step two, we use Random Forest as a classification algorithm. We have used kba2013 annotation for training. Features used were googcle-cross-lingual dictionary, Jaccrd similarity, Cosine similarity, KL-divergence, PageRnk scores, Right and Left context, first and last mention positions, body length, first pos form, mentioning body.

gatordsr-gatordsr_final¶

Participants | Proceedings | Input | Appendix

Run ID: gatordsr-gatordsr_final
Participant: gatordsr
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/1/2013
Type: automatic
Task: kba-ssf-2013
MD5: 0cf9b1e88dff1d833a5a2e3eece24507
Run description: Document extraction using query entity matching with aliases, sentence extraction using alias matching and coreference. Slot extraction using patterns, NER tags and NP tags. 158,052 documents with query entities, 30,326 unique extracted slot values for 8 slots and 146 entities, 4 slots and 24 entities missing.

gatordsr-gatordsr_infer¶

Participants | Proceedings | Input | Appendix

Run ID: gatordsr-gatordsr_infer
Participant: gatordsr
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/4/2013
Type: automatic
Task: kba-ssf-2013
MD5: db23439af6013c7d5f79f5cf0e7a148d
Run description: Document extraction using query entity matching with aliases, sentence extraction using alias matching and coreference. Slot extraction using patterns, NER tags and NP tags. 158,052 documents with query entities, 168,006 unique extracted slot values for 12 slots and 141 entities, 1 slots and 29 entities missing.

gatordsr-gatordsr_new¶

Participants | Proceedings | Input | Appendix

Run ID: gatordsr-gatordsr_new
Participant: gatordsr
Track: Knowledge Base Acceleration
Year: 2013
Submission: 6/12/2013
Type: automatic
Task: kba-ssf-2013
MD5: 0099ecd0d71d72546f42c5f6ed1e676f
Run description: Document extraction using query entity matching with aliases, sentence extraction using alias matching and co-reference. Slot extraction using patterns, NER tags and NP tags. 158,052 documents with query entities, 17885 unique extracted slot values for 8 slots and 139 entities, 4 slots and 31 entities missing.

IRIT-sig_irit_1¶

Participants | Proceedings | Input | Appendix

Run ID: IRIT-sig_irit_1
Participant: IRIT
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/28/2013
Type: automatic
Task: kba-ccr-2013
MD5: 1e5d3b824416479fb5eac54ceb7cc7b7
Run description: Entity title and some predicates values from DBpedia are used as as surface form names, then any document containing one of the surface form names is keeped using lucene, then extracted some properties of vital documents from the given training data, and finally, extract these properties from all documents and apply a supervised classifer RandomForest

IRIT-sig_irit_2¶

Participants | Proceedings | Input | Appendix

Run ID: IRIT-sig_irit_2
Participant: IRIT
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/28/2013
Type: automatic
Task: kba-ccr-2013
MD5: e3fa1b2ff44fdb36f4b79810a9465af0
Run description: Entity title and some predicates values from DBpedia are used as surface form names, then any document containing one of the surface form names is keeped using lucene, then we extracted some properties of vital documents from the given training data, and finally, extract these properties from all documents and apply a supervised classifer RandomForest

IRIT-sig_irit_3¶

Participants | Proceedings | Input | Appendix

Run ID: IRIT-sig_irit_3
Participant: IRIT
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/28/2013
Type: automatic
Task: kba-ccr-2013
MD5: f2358d57c57c7629876efab3bddb08b5
Run description: Entity title and some predicates values from DBpedia are used as surface form names, then any document containing one of the surface form names is keeped using lucene, then we extracted some properties of vital documents from the given training data, and finally, extract these properties from all documents and apply a supervised classifer RandomForest

LSIS_LIA-no_update_S4¶

Participants | Proceedings | Input | Appendix

Run ID: LSIS_LIA-no_update_S4
Participant: LSIS_LIA
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: b45fef02abaa803191d7230e218642e3
Run description: S4 Classifier Score = S_c1 if S_c1 < 0.5; Score = 0.5+ (S_c1*S_c2)/2 else; The class [Garbage < 0.25; 0.25 <= Neutral < 0.5; 0.5 <= Useful < 0.75; vital >= 0.75] is based on Score

LSIS_LIA-no_update_S4_2¶

Participants | Proceedings | Input | Appendix

Run ID: LSIS_LIA-no_update_S4_2
Participant: LSIS_LIA
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: c16134c8e94a6bc050a6533de700e64b
Run description: S4Bis Classifier Score = S_c1 if S_c1 < 0.5; Score = 0.5+ (S_c1*S_c2)/2 else; The class [Garbage < 0.5; 0.5 <= Neutral] for S_c1 [Useful < 0.5; 0.5 <= vital] for S_c2

LSIS_LIA-no_update_S4_3¶

Participants | Proceedings | Input | Appendix

Run ID: LSIS_LIA-no_update_S4_3
Participant: LSIS_LIA
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 29ecfb16346fada0e68d9a0df211e04a
Run description: S4Tris Classifier Score = S_c1 if S_c1 < 0.5; Score = 0.5+ (S_c2)/2 else; The class [Garbage < 0.5; 0.5 <= Neutral] for S_c1 [Useful < 0.5; 0.5 <= vital] for S_c2

LSIS_LIA-upd_doc_S4_2¶

Participants | Proceedings | Input | Appendix

Run ID: LSIS_LIA-upd_doc_S4_2
Participant: LSIS_LIA
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: f4293ebb6af153121a3f39a9b7dc1b24
Run description: S4Bis Classifier Score = S_c1 if S_c1 < 0.5; Score = 0.5+ (S_c1*S_c2)/2 else; The class [Garbage < 0.5; 0.5 <= Neutral] for S_c1 [Useful < 0.5; 0.5 <= vital] for S_c2

LSIS_LIA-upd_doc_S4_3¶

Participants | Proceedings | Input | Appendix

Run ID: LSIS_LIA-upd_doc_S4_3
Participant: LSIS_LIA
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: b467d174957c0498062860919a1c18fd
Run description: S4Tris Classifier Score = S_c1 if S_c1 < 0.5; Score = 0.5+ (S_c2)/2 else; The class [Garbage < 0.5; 0.5 <= Neutral] for S_c1 [Useful < 0.5; 0.5 <= vital] for S_c2

LSIS_LIA-upd_document_S4¶

Participants | Proceedings | Input | Appendix

Run ID: LSIS_LIA-upd_document_S4
Participant: LSIS_LIA
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 9b78bea710cccb7bef01d655c43fa1d3
Run description: S4 Classifier Score = S_c1 if S_c1 < 0.5; Score = 0.5+ (S_c1*S_c2)/2 else; The class [Garbage < 0.25; 0.25 <= Neutral < 0.5; 0.5 <= Useful < 0.75; vital >= 0.75] is based on Score

LSIS_LIA-upd_snippet_S4¶

Participants | Proceedings | Input | Appendix

Run ID: LSIS_LIA-upd_snippet_S4
Participant: LSIS_LIA
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: fa363daa9bce46da67cd29cbced975a5
Run description: S4 Classifier Score = S_c1 if S_c1 < 0.5; Score = 0.5+ (S_c1*S_c2)/2 else; The class [Garbage < 0.25; 0.25 <= Neutral < 0.5; 0.5 <= Useful < 0.75; vital >= 0.75] is based on Score

LSIS_LIA-upd_snpt_S4_2¶

Participants | Proceedings | Input | Appendix

Run ID: LSIS_LIA-upd_snpt_S4_2
Participant: LSIS_LIA
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 58451d032753a61e97cf27776ff01bee
Run description: S4Bis Classifier Score = S_c1 if S_c1 < 0.5; Score = 0.5+ (S_c1*S_c2)/2 else; The class [Garbage < 0.5; 0.5 <= Neutral] for S_c1 [Useful < 0.5; 0.5 <= vital] for S_c2

LSIS_LIA-upd_snpt_S4_3¶

Participants | Proceedings | Input | Appendix

Run ID: LSIS_LIA-upd_snpt_S4_3
Participant: LSIS_LIA
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 49e80b87cbeef8ec15e9ea6091a7ff32
Run description: S4Tris Classifier Score = S_c1 if S_c1 < 0.5; Score = 0.5+ (S_c2)/2 else; The class [Garbage < 0.5; 0.5 <= Neutral] for S_c1 [Useful < 0.5; 0.5 <= vital] for S_c2

PRIS-pris0¶

Participants | Proceedings | Input | Appendix

Run ID: PRIS-pris0
Participant: PRIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 6/12/2013
Type: automatic
Task: kba-ccr-2013
MD5: 38b44e117b676a65ffacab40669b3b7f
Run description: look for relative documents in elastcsearch index with exact entity name and alias as final results,set all the confidence score 1000

PRIS-pris1¶

Participants | Proceedings | Input | Appendix

Run ID: PRIS-pris1
Participant: PRIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 6/12/2013
Type: automatic
Task: kba-ccr-2013
MD5: 1829c08591d53c4125e34cab10509f28
Run description: looks for relative documents in elastcsearch index with entity name, alias and query expansion wordsas search results. choose wiki page of each entity,turn it in to bag of words and select documents from seach results that has more than 10% words of the bag as final results

PRIS-pris2¶

Participants | Proceedings | Input | Appendix

Run ID: PRIS-pris2
Participant: PRIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 6/12/2013
Type: automatic
Task: kba-ccr-2013
MD5: 826f57c1ac70ef2dc78fc8e0dee42d64
Run description: looks for relative documents in elastcsearch index with entity name, alias and query expansion wordsas search results. choose at least 10 key words of each entity and select documents from seach results that has more than 60% key words of the set as final results

PRIS-pris3¶

Participants | Proceedings | Input | Appendix

Run ID: PRIS-pris3
Participant: PRIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 6/12/2013
Type: automatic
Task: kba-ccr-2013
MD5: 6f761c2b582bfdc4931b2742fd85a01f
Run description: looks for relative documents in elastcsearch index with entity name, alias and query expansion words as search results. choose documents both in pris1 run and pris2 run

PRIS-pris_baseline¶

Participants | Proceedings | Input | Appendix

Run ID: PRIS-pris_baseline
Participant: PRIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/2/2013
Type: automatic
Task: kba-ccr-2013
MD5: bff860824ee37b2da4bd2f5c2accf80d
Run description: look for relative documents in elastcsearch index with exact entity name and alias as final results,set all the confidence score 1000

PRIS-pris_expansion¶

Participants | Proceedings | Input | Appendix

Run ID: PRIS-pris_expansion
Participant: PRIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/2/2013
Type: automatic
Task: kba-ccr-2013
MD5: 4ad4862ca560eb21fe1331ee6c1fcf45
Run description: expanded words are from training data about 3000+ documents relevant to each most entity and also wikipedia pages; choose almost 100 key words of each entity and select documents from seach results according to the expansion score

PRIS-pris_keywords¶

Participants | Proceedings | Input | Appendix

Run ID: PRIS-pris_keywords
Participant: PRIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/2/2013
Type: automatic
Task: kba-ccr-2013
MD5: 2ff296baf1e93e5b95128f7c2f606880
Run description: looks for relative documents in elastcsearch index with entity name, alias and query expansion wordsas search results. choose at least 10 key words of each entity and select documents from seach results that has more than 60% key words of the set as final results

PRIS-pris_merge¶

Participants | Proceedings | Input | Appendix

Run ID: PRIS-pris_merge
Participant: PRIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/2/2013
Type: automatic
Task: kba-ccr-2013
MD5: cfe4754a0dace9f2dd4e11faf5ff815e
Run description: looks for relative documents in elastcsearch index with entity name, alias and query expansion words as search results. choose documents both in pris1 run and pris2 run

PRIS-pris_similarity¶

Participants | Proceedings | Input | Appendix

Run ID: PRIS-pris_similarity
Participant: PRIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/2/2013
Type: automatic
Task: kba-ccr-2013
MD5: 906246e878ff03e05df72585cca14a15
Run description: looks for relative documents in elastcsearch index with entity name, alias and query expansion wordsas search results. choose wiki page of each entity,turn it in to bag of words and select documents from seach results that has more than 10% words of the bag as final results

PRIS-pris_ssf_0¶

Participants | Proceedings | Input | Appendix

Run ID: PRIS-pris_ssf_0
Participant: PRIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 6/12/2013
Type: automatic
Task: kba-ssf-2013
MD5: b2d8b80568e05fc3d1cc58649aea5f32
Run description: a distributed system builds the index of big data ,deals with information retrieval and fills slots with pre-trained patterns

PRIS-pris_ssf_1¶

Participants | Proceedings | Input | Appendix

Run ID: PRIS-pris_ssf_1
Participant: PRIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 6/12/2013
Type: automatic
Task: kba-ssf-2013
MD5: 5aebc48079448b429371a89d2fd91ca6
Run description: a distributed system builds the index of big data ,deals with information retrieval and fills slots with pre-trained patterns

PRIS-pris_ssf_2¶

Participants | Proceedings | Input | Appendix

Run ID: PRIS-pris_ssf_2
Participant: PRIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 6/13/2013
Type: automatic
Task: kba-ssf-2013
MD5: f1a3c62a093140fb7c3bbd7cbfa88403
Run description: a distributed system builds the index of big data ,deals with information retrieval and fills slots with pre-trained patterns

PRIS-pris_ssf_fst¶

Participants | Proceedings | Input | Appendix

Run ID: PRIS-pris_ssf_fst
Participant: PRIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ssf-2013
MD5: 37abfa4e759790f1a528cd56d7c797fc
Run description: a distributed system builds the index of big data ,deals with information retrieval and fills slots with pre-trained patterns

PRIS-pris_ssf_second¶

Participants | Proceedings | Input | Appendix

Run ID: PRIS-pris_ssf_second
Participant: PRIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ssf-2013
MD5: 92c4cde2647b789e14a6c322861dba16
Run description: distributed system builds the index of big data ,deals with information retrieval and fills slots with pre-trained patterns

PRIS-pris_svd¶

Participants | Proceedings | Input | Appendix

Run ID: PRIS-pris_svd
Participant: PRIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/3/2013
Type: automatic
Task: kba-ccr-2013
MD5: eecc4679f97ab3ac841145ffc75bedd9
Run description: taking all search-related documents into term-document matrix and modeling a lsi model; taking the certain wikipedia page as query to search query-related documents in the model.

RetrieWin-Submission_2¶

Participants | Input | Appendix

Run ID: RetrieWin-Submission_2
Participant: RetrieWin
Track: Knowledge Base Acceleration
Year: 2013
Submission: 6/12/2013
Type: automatic
Task: kba-ssf-2013
MD5: cc6254c60e3268ffecc96f7a1c6833a4
Run description: Collapses entity title strings and documents into sets of words and looks for fraction of exact match overlap with entity titles. Confidence is fraction of entity title words that appear in doc.

SCU-ssf_1¶

Participants | Proceedings | Input | Appendix

Run ID: SCU-ssf_1
Participant: SCU
Track: Knowledge Base Acceleration
Year: 2013
Submission: 6/13/2013
Type: automatic
Task: kba-ssf-2013
MD5: 4e0b10f5a6b051393b211bb65ac86544
Run description: Filter exact match, no duplicate doc id, remove negative relevance rating, byte range from clean visible

SCU-ssf_2¶

Participants | Proceedings | Input | Appendix

Run ID: SCU-ssf_2
Participant: SCU
Track: Knowledge Base Acceleration
Year: 2013
Submission: 6/13/2013
Type: automatic
Task: kba-ssf-2013
MD5: 247b8504d4c855604d175532f3f0ca7c
Run description: Filter exact match, no duplicate doc id, keep all relevance rating, byte range from clean visible

SCU-ssf_3¶

Participants | Proceedings | Input | Appendix

Run ID: SCU-ssf_3
Participant: SCU
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/4/2013
Type: automatic
Task: kba-ssf-2013
MD5: dda802675163674b5cbad0177a2ffdaa
Run description: Keep confidence score, force relevance rating to 2, byte range from clean visible

SCU-ssf_4¶

Participants | Proceedings | Input | Appendix

Run ID: SCU-ssf_4
Participant: SCU
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/4/2013
Type: automatic
Task: kba-ssf-2013
MD5: 4928472e3f94ff7974f2d9e94139b26b
Run description: scale confidence score to the range 800-1000 for certain slots, keep all output

SCU-ssf_5¶

Participants | Proceedings | Input | Appendix

Run ID: SCU-ssf_5
Participant: SCU
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ssf-2013
MD5: c186202d3a35bc43e7623780292218f5
Run description: map confidence score to 400-1000, keep greater or equal 500

UAmsterdam-bl_na_wChis_c1¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-bl_na_wChis_c1
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/26/2013
Type: automatic
Task: kba-ccr-2013
MD5: 335b29ed42dd3693c0d62a58e08a80cb
Run description: Settings file settings_wChis_linear_5_100_100_conf1, bDirichletNB_Tchi True, iNrOfBuckets 100, sTimeBucketUnit examples, iTimeBucketLength 100, fConfidenceThreshold -100, bNoNewFeatureSelection True, sConfidenceScore confidence1, sDecayFunction linear, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedChis

UAmsterdam-bl_na_wChis_c3¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-bl_na_wChis_c3
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/26/2013
Type: automatic
Task: kba-ccr-2013
MD5: 38af12b6ad76f69e54d7941b4bbf7780
Run description: Settings file settings_wChis_linear_5_100_100_conf3, bDirichletNB_Tchi True, iNrOfBuckets 100, sTimeBucketUnit examples, iTimeBucketLength 100, fConfidenceThreshold -100, bNoNewFeatureSelection True, sConfidenceScore confidence3, sDecayFunction linear, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedChis

UAmsterdam-bl_na_wConcs_c1¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-bl_na_wConcs_c1
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/26/2013
Type: automatic
Task: kba-ccr-2013
MD5: f69f58d09c13df9fd31a56b75a42cbbe
Run description: Settings file settings_wConcs_linear_5_100_100_conf1, bDirichletNB_Tchi True, iNrOfBuckets 100, sTimeBucketUnit examples, iTimeBucketLength 100, fConfidenceThreshold -100, bNoNewFeatureSelection True, sConfidenceScore confidence1, sDecayFunction linear, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedConcs

UAmsterdam-bl_na_wConcs_c3¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-bl_na_wConcs_c3
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/26/2013
Type: automatic
Task: kba-ccr-2013
MD5: 1086ca688c9c735f22c79f0ae8bc25c3
Run description: Settings file settings_wConcs_linear_5_100_100_conf3, bDirichletNB_Tchi True, iNrOfBuckets 100, sTimeBucketUnit examples, iTimeBucketLength 100, fConfidenceThreshold -100, bNoNewFeatureSelection True, sConfidenceScore confidence3, sDecayFunction linear, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedConcs

UAmsterdam-bsln_5_100_100¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-bsln_5_100_100
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/19/2013
Type: automatic
Task: kba-ccr-2013
MD5: c0359809d328f3e703b379a5965b9831
Run description: Feature file settingsBaselineNoAdaption, bDirichletNB_Tchi True, iNrOfBuckets 100, sTimeBucketUnit examples, iTimeBucketLength 100, sDecayFunction flat, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sChi weightedConcs

UAmsterdam-uva_kba_run_1¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-uva_kba_run_1
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/24/2013
Type: automatic
Task: kba-ccr-2013
MD5: c998ebda0f5395d5e6d1661b8a6c0f63
Run description: Settings file settings_1, bDirichletNB_Tchi True, iNrOfBuckets 10, sTimeBucketUnit examples, iTimeBucketLength 500, fConfidenceThreshold -200, sConfidenceScore confidence1, sDecayFunction linear, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedConcs

UAmsterdam-uva_kba_run_10¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-uva_kba_run_10
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/28/2013
Type: automatic
Task: kba-ccr-2013
MD5: 589e571bb7f2691f5e608badcbc1a66a
Run description: Settings file settings_10, bDirichletNB_Tchi True, iNrOfBuckets 80, sTimeBucketUnit examples, iTimeBucketLength 70, fConfidenceThreshold -75, sConfidenceScore confidence1, sDecayFunction linear, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedChis

UAmsterdam-uva_kba_run_11¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-uva_kba_run_11
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/27/2013
Type: automatic
Task: kba-ccr-2013
MD5: e11cf849a4152a81cce84c838bf882ac
Run description: Settings file settings_11, bDirichletNB_Tchi True, iNrOfBuckets 80, sTimeBucketUnit examples, iTimeBucketLength 50, fConfidenceThreshold -75, sConfidenceScore confidence3, sDecayFunction linear, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedChis

UAmsterdam-uva_kba_run_12¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-uva_kba_run_12
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/27/2013
Type: automatic
Task: kba-ccr-2013
MD5: b3508f8eb6d2a3d49d1c8cb47288839c
Run description: Settings file settings_12, bDirichletNB_Tchi True, iNrOfBuckets 80, sTimeBucketUnit examples, iTimeBucketLength 70, fConfidenceThreshold -75, sConfidenceScore confidence3, sDecayFunction linear, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedChis

UAmsterdam-uva_kba_run_13¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-uva_kba_run_13
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/28/2013
Type: automatic
Task: kba-ccr-2013
MD5: 79cb855d0c0ba41f52c2d969005530e1
Run description: Settings file settings_13, bDirichletNB_Tchi True, iNrOfBuckets 80, sTimeBucketUnit examples, iTimeBucketLength 50, fConfidenceThreshold -75, sConfidenceScore confidence1, sDecayFunction flat, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedChis

UAmsterdam-uva_kba_run_14¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-uva_kba_run_14
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/27/2013
Type: automatic
Task: kba-ccr-2013
MD5: 0ef18d04b2eb7a7c16d124c538bc63ca
Run description: Settings file settings_14, bDirichletNB_Tchi True, iNrOfBuckets 80, sTimeBucketUnit examples, iTimeBucketLength 70, fConfidenceThreshold -75, sConfidenceScore confidence1, sDecayFunction flat, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedChis

UAmsterdam-uva_kba_run_15¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-uva_kba_run_15
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/27/2013
Type: automatic
Task: kba-ccr-2013
MD5: 00e0106f248826099de0255e02360a42
Run description: Settings file settings_15, bDirichletNB_Tchi True, iNrOfBuckets 80, sTimeBucketUnit examples, iTimeBucketLength 50, fConfidenceThreshold -75, sConfidenceScore confidence3, sDecayFunction flat, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedChis

UAmsterdam-uva_kba_run_16¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-uva_kba_run_16
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/27/2013
Type: automatic
Task: kba-ccr-2013
MD5: 5126c7613ab24ebc89dd3592f7e6c6ae
Run description: Settings file settings_16, bDirichletNB_Tchi True, iNrOfBuckets 80, sTimeBucketUnit examples, iTimeBucketLength 70, fConfidenceThreshold -75, sConfidenceScore confidence3, sDecayFunction flat, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedChis

UAmsterdam-uva_kba_run_2¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-uva_kba_run_2
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/26/2013
Type: automatic
Task: kba-ccr-2013
MD5: c27c572be1e4d504febb9b877817eebe
Run description: Settings file settings_2, bDirichletNB_Tchi True, iNrOfBuckets 40, sTimeBucketUnit examples, iTimeBucketLength 70, fConfidenceThreshold -200, sConfidenceScore confidence1, sDecayFunction linear, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedConcs

UAmsterdam-uva_kba_run_3¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-uva_kba_run_3
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/26/2013
Type: automatic
Task: kba-ccr-2013
MD5: ea4f4e24648d1919eb68174f28b140c6
Run description: Settings file settings_3, bDirichletNB_Tchi True, iNrOfBuckets 10, sTimeBucketUnit examples, iTimeBucketLength 500, fConfidenceThreshold -200, sConfidenceScore confidence3, sDecayFunction linear, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedConcs

UAmsterdam-uva_kba_run_4¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-uva_kba_run_4
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/26/2013
Type: automatic
Task: kba-ccr-2013
MD5: 69726ae101c6157ae6c8a94bca19d1ac
Run description: Settings file settings_4, bDirichletNB_Tchi True, iNrOfBuckets 40, sTimeBucketUnit examples, iTimeBucketLength 70, fConfidenceThreshold -200, sConfidenceScore confidence3, sDecayFunction linear, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedConcs

UAmsterdam-uva_kba_run_5¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-uva_kba_run_5
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/26/2013
Type: automatic
Task: kba-ccr-2013
MD5: 04faf9b69486ae32b975040c31497270
Run description: Settings file settings_5, bDirichletNB_Tchi True, iNrOfBuckets 10, sTimeBucketUnit examples, iTimeBucketLength 500, fConfidenceThreshold -200, sConfidenceScore confidence1, sDecayFunction linear, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedChis

UAmsterdam-uva_kba_run_6¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-uva_kba_run_6
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/26/2013
Type: automatic
Task: kba-ccr-2013
MD5: f666397aeafbf4422ec4668205149c96
Run description: Settings file settings_6, bDirichletNB_Tchi True, iNrOfBuckets 40, sTimeBucketUnit examples, iTimeBucketLength 70, fConfidenceThreshold -200, sConfidenceScore confidence1, sDecayFunction linear, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedChis

UAmsterdam-uva_kba_run_7¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-uva_kba_run_7
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/26/2013
Type: automatic
Task: kba-ccr-2013
MD5: 69eb40d7c6757d075c3c5d9659f37926
Run description: Settings file settings_7, bDirichletNB_Tchi True, iNrOfBuckets 10, sTimeBucketUnit examples, iTimeBucketLength 500, fConfidenceThreshold -200, sConfidenceScore confidence3, sDecayFunction linear, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedChis

UAmsterdam-uva_kba_run_8¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-uva_kba_run_8
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/26/2013
Type: automatic
Task: kba-ccr-2013
MD5: d25be2d64c3bc2af9a3b98ad931e85c3
Run description: Settings file settings_8, bDirichletNB_Tchi True, iNrOfBuckets 40, sTimeBucketUnit examples, iTimeBucketLength 70, fConfidenceThreshold -200, sConfidenceScore confidence3, sDecayFunction linear, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedChis

UAmsterdam-uva_kba_run_9¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-uva_kba_run_9
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/27/2013
Type: automatic
Task: kba-ccr-2013
MD5: 3f29d5b874ca4fee532bd3b82fbaf0d7
Run description: Settings file settings_9, bDirichletNB_Tchi True, iNrOfBuckets 80, sTimeBucketUnit examples, iTimeBucketLength 50, fConfidenceThreshold -75, sConfidenceScore confidence1, sDecayFunction linear, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedChis

UAmsterdam-uva_kba_run_av¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-uva_kba_run_av
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/28/2013
Type: automatic
Task: kba-ccr-2013
MD5: 5318c1a4997f3ae70d6c6a189096bd92
Run description: Every document in which a mention is found is considered to be vital.

UAmsterdam-uva_run_wChi_c1¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-uva_run_wChi_c1
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/26/2013
Type: automatic
Task: kba-ccr-2013
MD5: 510dee3939250c44c4667ec04b7689c2
Run description: Settings file settings_wChis_linear_5_100_100_confidence1, bDirichletNB_Tchi True, iNrOfBuckets 100, sTimeBucketUnit examples, iTimeBucketLength 100, fConfidenceThreshold -100, sConfidenceScore confidence1, sDecayFunction linear, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedChis

UAmsterdam-uva_run_wChi_c3¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-uva_run_wChi_c3
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/26/2013
Type: automatic
Task: kba-ccr-2013
MD5: fe7c95d3d9b23dd1d57dd6d50c2f3359
Run description: Settings file settings_wChis_linear_5_100_100_confidence3, bDirichletNB_Tchi True, iNrOfBuckets 100, sTimeBucketUnit examples, iTimeBucketLength 100, fConfidenceThreshold -100, sConfidenceScore confidence3, sDecayFunction linear, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedChis

UAmsterdam-uva_run_wCon_c1¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-uva_run_wCon_c1
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/26/2013
Type: automatic
Task: kba-ccr-2013
MD5: 71b66c9a97d059b37689265391a32fdd
Run description: Settings file settings_wConcs_linear_5_100_100_confidence1, bDirichletNB_Tchi True, iNrOfBuckets 100, sTimeBucketUnit examples, iTimeBucketLength 100, fConfidenceThreshold -100, sConfidenceScore confidence1, sDecayFunction linear, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedConcs

UAmsterdam-uva_run_wCon_c3¶

Participants | Proceedings | Input | Appendix

Run ID: UAmsterdam-uva_run_wCon_c3
Participant: UAmsterdam
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/26/2013
Type: automatic
Task: kba-ccr-2013
MD5: f00a90c4f1b7aba6e8e73a34f2c36ba5
Run description: Settings file settings_wConcs_linear_5_100_100_confidence3, bDirichletNB_Tchi True, iNrOfBuckets 100, sTimeBucketUnit examples, iTimeBucketLength 100, fConfidenceThreshold -100, sConfidenceScore confidence3, sDecayFunction linear, iMaxNrOfFeatures 5, iNrOfFeatures 588693, sAdaptationMode pseudo, sChi weightedConcs

udel_fang-UDInfoK_Ex¶

Participants | Proceedings | Input | Appendix

Run ID: udel_fang-UDInfoK_Ex
Participant: udel_fang
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/27/2013
Type: automatic
Task: kba-ccr-2013
MD5: 1af4a3684ae6a8c2e12a86fba158be54
Run description: For each topic entity, the surface name variations are collected from DBPedia and Wikipedia. If a document has exact match with the topic entity or one of its surface name variations, it will be labeled as vital.

udel_fang-UDInfoK_Weight1¶

Participants | Proceedings | Input | Appendix

Run ID: udel_fang-UDInfoK_Weight1
Participant: udel_fang
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/27/2013
Type: automatic
Task: kba-ccr-2013
MD5: 4d42b865492f2a5bbabe402e91d909d7
Run description: For each topic entity, the surface name variations are collected from DBPedia and Wikipedia. Moreover, the related entities which connect to the topic entity in Wikipedia graph will also be collected, and the weight of each related entity will be estimated based on the training data. If a document has exact match with the topic entity or one of its surface name variations, it will be labeled as vital. The confidence score is determined by the number of related entity mentions and their weights in the document. Documents with confidence score above the threshold will be preserved.

udel_fang-UDInfoK_Weight2¶

Participants | Proceedings | Input | Appendix

Run ID: udel_fang-UDInfoK_Weight2
Participant: udel_fang
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/27/2013
Type: automatic
Task: kba-ccr-2013
MD5: 8e4944097eb6bb03e7289c8ba60dad71
Run description: For each topic entity, the surface name variations are collected from DBPedia and Wikipedia. Moreover, the related entities which connect to the topic entity in Wikipedia graph will also be collected, and the weight of each related entity will be estimated based on the training data. If a document has exact match with the topic entity or one of its surface name variations, it will be labeled as vital. The confidence score is determined by the number of related entity mentions and their weights in the document. Documents with confidence score above the threshold will be preserved.

udel_fang-UDInfoK_Wiki1¶

Participants | Proceedings | Input | Appendix

Run ID: udel_fang-UDInfoK_Wiki1
Participant: udel_fang
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/27/2013
Type: automatic
Task: kba-ccr-2013
MD5: 9aa98f2c7c6cb52ec08f82f4d001c118
Run description: For each topic entity, the surface name variations are collected from DBPedia and Wikipedia. Moreover, the related entities which connect to the topic entity in Wikipedia graph will also be collected. If a document has exact match with the topic entity or one of its surface name variations, it will be labeled as vital. The confidence score is determined by the number of related entity mentions in the document. Documents with confidence score above the threshold will be preserved.

udel_fang-UDInfoK_Wiki2¶

Participants | Proceedings | Input | Appendix

Run ID: udel_fang-UDInfoK_Wiki2
Participant: udel_fang
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/27/2013
Type: automatic
Task: kba-ccr-2013
MD5: 786852dec21985cc76e2003b59608332
Run description: For each topic entity, the surface name variations are collected from DBPedia and Wikipedia. Moreover, the related entities which connect to the topic entity in Wikipedia graph will also be collected. If a document has exact match with the topic entity or one of its surface name variations, it will be labeled as vital. The confidence score is determined by the number of related entity mentions in the document. Documents with confidence score above the threshold will be preserved.

uiucGSLIS-bayes01¶

Participants | Input | Appendix

Run ID: uiucGSLIS-bayes01
Participant: uiucGSLIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/30/2013
Type: automatic
Task: kba-ccr-2013
MD5: 7ec6618fa0b5a26c4b8d141b29506f4c
Run description: bayes updated models from vital fb. mu=2500. window=200

uiucGSLIS-bayes02¶

Participants | Input | Appendix

Run ID: uiucGSLIS-bayes02
Participant: uiucGSLIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/30/2013
Type: automatic
Task: kba-ccr-2013
MD5: 7298af2f205acd4b369453d2e2301278
Run description: bayes updated models from vital fb. mu=150. window=20

uiucGSLIS-bayes03¶

Participants | Input | Appendix

Run ID: uiucGSLIS-bayes03
Participant: uiucGSLIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/30/2013
Type: automatic
Task: kba-ccr-2013
MD5: ed7f84f42ddc21445df5c2c0df237a1f
Run description: bayes updated models from vital fb. mu=2500. window=20

uiucGSLIS-bayes04¶

Participants | Input | Appendix

Run ID: uiucGSLIS-bayes04
Participant: uiucGSLIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/30/2013
Type: automatic
Task: kba-ccr-2013
MD5: 3323cb8146fbf0e0f59ca1b4cd8ae751
Run description: bayes updated models from vital fb. mu=2500. window=20

uiucGSLIS-bayes05¶

Participants | Input | Appendix

Run ID: uiucGSLIS-bayes05
Participant: uiucGSLIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/30/2013
Type: automatic
Task: kba-ccr-2013
MD5: 4453ce27ebf8a99237c89ea1b06caef6
Run description: bayes updated models from vital fb. mu=5000. window=20

uiucGSLIS-bayes06¶

Participants | Input | Appendix

Run ID: uiucGSLIS-bayes06
Participant: uiucGSLIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/30/2013
Type: automatic
Task: kba-ccr-2013
MD5: 4e02e3e8a33949dd910bcb39b56a899d
Run description: bayes updated models from vital fb. mu=1500. window=50

uiucGSLIS-bayes07¶

Participants | Input | Appendix

Run ID: uiucGSLIS-bayes07
Participant: uiucGSLIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/30/2013
Type: automatic
Task: kba-ccr-2013
MD5: 197edadb39ac3d223b8b20763a9a58bd
Run description: bayes updated models from vital fb. mu=2500. window=50

uiucGSLIS-bayes08¶

Participants | Input | Appendix

Run ID: uiucGSLIS-bayes08
Participant: uiucGSLIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/30/2013
Type: automatic
Task: kba-ccr-2013
MD5: 4ee4f34f650227962871a2f583be13df
Run description: CHANGE ME

uiucGSLIS-bayes09¶

Participants | Input | Appendix

Run ID: uiucGSLIS-bayes09
Participant: uiucGSLIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/30/2013
Type: automatic
Task: kba-ccr-2013
MD5: 58bf2c1598436531c9e10c3c9e308773
Run description: CHANGE ME

uiucGSLIS-static01¶

Participants | Input | Appendix

Run ID: uiucGSLIS-static01
Participant: uiucGSLIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/29/2013
Type: automatic
Task: kba-ccr-2013
MD5: 02abee27e16c78f84e3e2f6c250b6511
Run description: simple wikitext baseline. optimized on 'vital'

uiucGSLIS-static02¶

Participants | Input | Appendix

Run ID: uiucGSLIS-static02
Participant: uiucGSLIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/29/2013
Type: automatic
Task: kba-ccr-2013
MD5: 40faa36e609e01708eec341e833fbf6e
Run description: static system with training-based relevance feedback models (all vital)

uiucGSLIS-static03¶

Participants | Input | Appendix

Run ID: uiucGSLIS-static03
Participant: uiucGSLIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/30/2013
Type: automatic
Task: kba-ccr-2013
MD5: ee1b2a7841eb967a4ea1617d647cde28
Run description: CHANGE ME

uiucGSLIS-static04¶

Participants | Input | Appendix

Run ID: uiucGSLIS-static04
Participant: uiucGSLIS
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/30/2013
Type: automatic
Task: kba-ccr-2013
MD5: 380db043cdd4105f08af3cfe3026ad2c
Run description: CHANGE ME

UMass_CIIR-T2ELMax¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-T2ELMax
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 6ac31d6ee217bc9c6e2e23ea756e3492
Run description: Entity Linked top 2 docs from SDM for each entity for each week; max linking score.

UMass_CIIR-T2ELMax_1¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-T2ELMax_1
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/4/2013
Type: automatic
Task: kba-ccr-2013
MD5: c6dfd4df11a70ffa7a990a8c4ac5017b
Run description: Entity Linked top 2 docs from SDM for each entity for each week; max linking score with a -1.0 threshold.

UMass_CIIR-T2ELMax_1_tw¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-T2ELMax_1_tw
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 0ac6b34fa2e0876c548df6dcf0811ec0
Run description: Entity Linked top 2 docs from SDM for each entity for each week; max linking score with a -1.0 threshold. Added top 2 docs from SDM for twitter ents.

UMass_CIIR-T2ELMax_TO¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-T2ELMax_TO
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/4/2013
Type: automatic
Task: kba-ccr-2013
MD5: d04e9fa0e21e18356f2a199bea514eca
Run description: Entity Linked top 2 docs from SDM for each entity for each week; max linking score; only top ranked entity.

UMass_CIIR-T2ELMax_TO_1_tw¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-T2ELMax_TO_1_tw
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 0a555603d08afcaaae35f0a8f58a2bc5
Run description: Entity Linked top 2 docs from SDM for each entity for each week; max linking score; only top ranked entity with a -1.0 threshold. Added top 2 docs from SDM for twitter ents.

UMass_CIIR-T2ELMax_TO_tw¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-T2ELMax_TO_tw
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 957ee10203eb5b36065df99f92afbcd5
Run description: Entity Linked top 2 docs from SDM for each entity for each week; max linking score; only top ranked entity. Added top 2 docs from SDM for twitter ents.

UMass_CIIR-T2ELMax_tw¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-T2ELMax_tw
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: d813f3b3d114ffabdcace4cdb670084e
Run description: Entity Linked top 2 docs from SDM for each entity for each week; max linking score. Added top 2 docs from SDM for twitter ents.

UMass_CIIR-T2ELMaxTO_1¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-T2ELMaxTO_1
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/4/2013
Type: automatic
Task: kba-ccr-2013
MD5: 21f5f579bb904b9ee017d9b8450391c8
Run description: Entity Linked top 2 docs from SDM for each entity for each week; max linking score; only top ranked entity with a -1.0 threshold.

UMass_CIIR-t2LinkProb_tw¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-t2LinkProb_tw
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/4/2013
Type: automatic
Task: kba-ccr-2013
MD5: 32f15dd6fb25063537c98249c106928b
Run description: Entity Linked top 2 docs from SDM for each entity for each week; maximum likelihood entity probability scoring. Added top 2 docs from SDM for twitter ents.

UMass_CIIR-top2LinkedProb¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-top2LinkedProb
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/4/2013
Type: automatic
Task: kba-ccr-2013
MD5: 4bb83d59ee74dd7a31992332b895e827
Run description: Entity Linked top 2 docs from SDM for each entity for each week; maximum likelihood entity probability scoring.

UMass_CIIR-wrm_trm_r¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wrm_trm_r
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 87a164bcd4f5427d35e0bba7367ef7de
Run description: Retrieval-based method. Retrieval model for wiki entities rm-sdm; Retrieval model for twitter entities rm-sdm; confidence prediction based on rank.

UMass_CIIR-wrm_trm_s¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wrm_trm_s
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 274909339571c2304bebfa430609cd0a
Run description: Retrieval-based method. Retrieval model for wiki entities rm-sdm; Retrieval model for twitter entities rm-sdm; confidence prediction based on score.

UMass_CIIR-wrm_tsdm_r¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wrm_tsdm_r
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 73dd03691c9081d83e8ec6ea1d2df174
Run description: Retrieval-based method. Retrieval model for wiki entities rm-sdm; Retrieval model for twitter entities sdm; confidence prediction based on rank.

UMass_CIIR-wrm_tsdm_s¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wrm_tsdm_s
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 8ba0416bfb3db38e382c3d45c1b9e319
Run description: Retrieval-based method. Retrieval model for wiki entities rm-sdm; Retrieval model for twitter entities sdm; confidence prediction based on score.

UMass_CIIR-wrm_tskq_r¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wrm_tskq_r
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 7aeed8a0dcd720c53ce14b3be5c79736
Run description: Retrieval-based method. Retrieval model for wiki entities rm-sdm; Retrieval model for twitter entities sketchQuery; confidence prediction based on rank.

UMass_CIIR-wrm_tskq_s¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wrm_tskq_s
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 8d9330bd3ffa7f8de36a7a2d30ce6dbf
Run description: Retrieval-based method. Retrieval model for wiki entities rm-sdm; Retrieval model for twitter entities sketchQuery; confidence prediction based on score.

UMass_CIIR-wrn_tsdm_r¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wrn_tsdm_r
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: b27dce7b89b5c7a2157f0af3c40cacd5
Run description: Retrieval-based method. Retrieval model for wiki entities entityRepr; Retrieval model for twitter entities sdm; confidence prediction based on rank.

UMass_CIIR-wrn_tsdm_s¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wrn_tsdm_s
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 00f075a203d5e8d3751c658e34306108
Run description: Retrieval-based method. Retrieval model for wiki entities entityRepr; Retrieval model for twitter entities sdm; confidence prediction based on score.

UMass_CIIR-wrn_tskq_s¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wrn_tskq_s
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 2943a80769c65f30fe055a1c4dfad971
Run description: Retrieval-based method. Retrieval model for wiki entities entityRepr; Retrieval model for twitter entities sketchQuery; confidence prediction based on score.

UMass_CIIR-wrt_tsdm_r¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wrt_tsdm_r
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 2a6cd4f2e75491182058ab5c150dad8a
Run description: Retrieval-based method. Retrieval model for wiki entities entityReprTextOnly; Retrieval model for twitter entities sdm; confidence prediction based on rank.

UMass_CIIR-wrt_tsdm_s¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wrt_tsdm_s
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: f1c21443e715fe24644c436e0cb6f478
Run description: Retrieval-based method. Retrieval model for wiki entities entityReprTextOnly; Retrieval model for twitter entities sdm; confidence prediction based on score.

UMass_CIIR-wrt_tskq_r¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wrt_tskq_r
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: cb4aebc7033b3b4460b657ffb0ec3a87
Run description: Retrieval-based method. Retrieval model for wiki entities entityReprTextOnly; Retrieval model for twitter entities sketchQuery; confidence prediction based on rank.

UMass_CIIR-wrt_tskq_s¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wrt_tskq_s
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: e5c721295027f454605a8f7a55c4be55
Run description: Retrieval-based method. Retrieval model for wiki entities entityReprTextOnly; Retrieval model for twitter entities sketchQuery; confidence prediction based on score.

UMass_CIIR-wrtn_tsdm_r¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wrtn_tsdm_r
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 709f60f8355e22d28cebe3b8c42d34f4
Run description: Retrieval-based method. Retrieval model for wiki entities entityReprTextNames; Retrieval model for twitter entities sdm; confidence prediction based on rank.

UMass_CIIR-wrtn_tsdm_s¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wrtn_tsdm_s
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 5c30caeb9fd50328ec82a0b572979981
Run description: Retrieval-based method. Retrieval model for wiki entities entityReprTextNames; Retrieval model for twitter entities sdm; confidence prediction based on score.

UMass_CIIR-wrtn_tskq_r¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wrtn_tskq_r
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 4b221cba61f027137e6a55b6b7102d74
Run description: Retrieval-based method. Retrieval model for wiki entities entityReprTextNames; Retrieval model for twitter entities sketchQuery; confidence prediction based on rank.

UMass_CIIR-wrtn_tskq_s¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wrtn_tskq_s
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 219107d25e34bb10ab9143c30ae63370
Run description: Retrieval-based method. Retrieval model for wiki entities entityReprTextNames; Retrieval model for twitter entities sketchQuery; confidence prediction based on score.

UMass_CIIR-wsdm_tsdm_r¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wsdm_tsdm_r
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 2e636359ae09ad986090687119f8f9c2
Run description: Retrieval-based method. Retrieval model for wiki entities sdm; Retrieval model for twitter entities sdm; confidence prediction based on rank.

UMass_CIIR-wsdm_tsdm_s¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wsdm_tsdm_s
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: f4acdaa5f32afc51eb5a3ada11708df9
Run description: Retrieval-based method. Retrieval model for wiki entities sdm; Retrieval model for twitter entities sdm; confidence prediction based on score.

UMass_CIIR-wskq_tsdm_r¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wskq_tsdm_r
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 1d51dd5904e127874bd1a2a69cbf8587
Run description: Retrieval-based method. Retrieval model for wiki entities sketchQuery; Retrieval model for twitter entities sdm; confidence prediction based on rank.

UMass_CIIR-wskq_tsdm_s¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wskq_tsdm_s
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 6e30c8b6b41e7dfedbb02b367928cd5f
Run description: Retrieval-based method. Retrieval model for wiki entities sketchQuery; Retrieval model for twitter entities sdm; confidence prediction based on score.

UMass_CIIR-wskq_tskq_r¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wskq_tskq_r
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: 1b301e840369785c9735e29b4e086cb7
Run description: Retrieval-based method. Retrieval model for wiki entities sketchQuery; Retrieval model for twitter entities sketchQuery; confidence prediction based on rank.

UMass_CIIR-wskq_tskq_s¶

Participants | Proceedings | Input | Appendix

Run ID: UMass_CIIR-wskq_tskq_s
Participant: UMass_CIIR
Track: Knowledge Base Acceleration
Year: 2013
Submission: 9/5/2013
Type: automatic
Task: kba-ccr-2013
MD5: a1824b5dcfed31334196b6fc0821d740
Run description: Retrieval-based method. Retrieval model for wiki entities sketchQuery; Retrieval model for twitter entities sketchQuery; confidence prediction based on score.

WiscDEFT-baseline¶

Participants | Proceedings | Input | Appendix

Run ID: WiscDEFT-baseline
Participant: WiscDEFT
Track: Knowledge Base Acceleration
Year: 2013
Submission: 6/13/2013
Type: automatic
Task: kba-ssf-2013
MD5: a5880b3967d73d5267d24d5a8e9960ec
Run description: Basic system built based on Wisconsin's KBP system with few additional rules for new relations.

WiscDEFT-baseline2¶

Participants | Proceedings | Input | Appendix

Run ID: WiscDEFT-baseline2
Participant: WiscDEFT
Track: Knowledge Base Acceleration
Year: 2013
Submission: 6/13/2013
Type: automatic
Task: kba-ssf-2013
MD5: 413b9ba74b454a59444643e40b138510
Run description: Basic system built based on Wisconsin's KBP system with few additional rules for new relations.

WiscDEFT-run1¶

Participants | Proceedings | Input | Appendix

Run ID: WiscDEFT-run1
Participant: WiscDEFT
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/26/2013
Type: manual
Task: kba-ssf-2013
MD5: fdfa5270886c50ff619e407ea4658083
Run description: Basic system built based on Wisconsin's KBP system with few additional rules for new relations.

WiscDEFT-run2¶

Participants | Proceedings | Input | Appendix

Run ID: WiscDEFT-run2
Participant: WiscDEFT
Track: Knowledge Base Acceleration
Year: 2013
Submission: 8/27/2013
Type: manual
Task: kba-ssf-2013
MD5: 47fe4225abf05f87c439b475d14e70f2
Run description: Basic system built based on Wisconsin's KBP system with few additional rules for new relations.

WiscDEFT-test¶

Participants | Proceedings | Input | Appendix

Run ID: WiscDEFT-test
Participant: WiscDEFT
Track: Knowledge Base Acceleration
Year: 2013
Submission: 6/11/2013
Type: automatic
Task: kba-ssf-2013
MD5: 9f40a04ac6635897ea6aeca111083290
Run description: Collapses entity title strings and documents into sets of words and looks for fraction of exact match overlap with entity titles. Confidence is fraction of entity title words that appear in doc.